This journal paper focuses on developing surrogate models for predicting the damage equivalent load (DEL) on wind turbines without needing extensive aeroelastic simulations. The study emphasizes the development of a sequential machine learning architecture for this purpose. The study also explores implementing simplified wake models and transfer learning to enhance the models' prediction capabilities in various wind conditions.

This study emphasizes the need for effective condition monitoring in permanent magnet offshore wind generators to tackle issues like demagnetization and eccentricity. Utilizing a machine learning model and high-resolution measurements, we explore methods of early fault detection. Our findings indicate that flux monitoring with affordable, easy-to-install stray flux sensors with frequency information offers a promising fault detection strategy for large megawatt-scale offshore wind generators.

The rising share of wind power poses challenges to cost-effective integration while ensuring reliability. Balancing the needs of the power system and contributions of wind power is crucial for long-term value. Research should prioritize wind power advantages over competitors, focussing on internal challenges. Collaboration with other technologies is essential for addressing the fundamental objectives of power systems – maintaining reliable supply–demand balance at the lowest cost.